lkml.org 
[lkml]   [2010]   [Mar]   [29]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: [PATCH 1/2] perf: Correctly align perf event tracing buffer
    On Mon, Mar 29, 2010 at 07:20:09PM +0200, Peter Zijlstra wrote:
    > On Mon, 2010-03-29 at 19:16 +0200, Frederic Weisbecker wrote:
    > > On Mon, Mar 29, 2010 at 10:51:31AM +0200, Peter Zijlstra wrote:
    > > > On Sun, 2010-03-28 at 07:11 +0200, Frederic Weisbecker wrote:
    > > > > kernel/trace/trace_event_perf.c | 11 +++++++++--
    > > > > 1 files changed, 9 insertions(+), 2 deletions(-)
    > > > >
    > > > > diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
    > > > > index 0709e4f..69941f3 100644
    > > > > --- a/kernel/trace/trace_event_perf.c
    > > > > +++ b/kernel/trace/trace_event_perf.c
    > > > > @@ -15,7 +15,12 @@ EXPORT_PER_CPU_SYMBOL_GPL(perf_trace_regs);
    > > > > static char *perf_trace_buf;
    > > > > static char *perf_trace_buf_nmi;
    > > > >
    > > > > -typedef typeof(char [PERF_MAX_TRACE_SIZE]) perf_trace_t ;
    > > > > +/*
    > > > > + * Force it to be aligned to unsigned long to avoid misaligned accesses
    > > > > + * suprises
    > > > > + */
    > > > > +typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
    > > > > + perf_trace_t;
    > > > >
    > > >
    > > > wouldn't __aligned(8) be simpler?
    > >
    > >
    > > David and Tejun seemed to prefer to create the alignment on the
    > > type level rather than using an align.
    > >
    > > I'm personally fine either way.
    >
    > Also, if you need u64 alignment, shouldn't you use u64 instead of
    > unsigned long, the alignment requirement on those two might differ on
    > 32bit machines.


    Yeah but we need the u64 alignment only on 64 bits machines.



    \
     
     \ /
      Last update: 2010-03-29 19:53    [W:0.024 / U:0.904 seconds]
    ©2003-2016 Jasper Spaans. hosted at Digital OceanAdvertise on this site